Phenology-Aware Machine Learning Framework for Chlorophyll Estimation in Cotton Using Hyperspectral Reflectance
Accurate and non-destructive monitoring of leaf chlorophyll content (LCC) is essential for assessing crop photosynthetic activity and nitrogen status in precision agriculture. This study introduces a phenology-aware machine learning framework that combines hyperspectral reflectance data with various...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/15/2713 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849239534883045376 |
|---|---|
| author | Chunbo Jiang Yi Cheng Yongfu Li Lei Peng Gangshang Dong Ning Lai Qinglong Geng |
| author_facet | Chunbo Jiang Yi Cheng Yongfu Li Lei Peng Gangshang Dong Ning Lai Qinglong Geng |
| author_sort | Chunbo Jiang |
| collection | DOAJ |
| description | Accurate and non-destructive monitoring of leaf chlorophyll content (LCC) is essential for assessing crop photosynthetic activity and nitrogen status in precision agriculture. This study introduces a phenology-aware machine learning framework that combines hyperspectral reflectance data with various regression models to estimate leaf chlorophyll content (LCC) in cotton at six key reproductive stages. Field experiments utilized synchronized spectral and SPAD measurements, incorporating spectral transformations—such as vegetation indices (VIs), first-order derivatives, and trilateration edge parameters (TEPs, a new set of geometric metrics for red-edge characterization)—for evaluation. Five regression approaches were evaluated, including univariate and multivariate linear models, along with three machine learning algorithms: Random Forest, K-Nearest Neighbor, and Support Vector Regression. Random Forest consistently outperformed the other models, achieving the highest R<sup>2</sup> (0.85) and the lowest RMSE (4.1) during the bud stage. Notably, the optimal prediction accuracy was achieved with fewer than five spectral features. The proposed framework demonstrates the potential for scalable, stage-specific monitoring of chlorophyll dynamics and offers valuable insights for large-scale crop management applications. |
| format | Article |
| id | doaj-art-b21c0a1d901c4592af034a178d5f2ec1 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-b21c0a1d901c4592af034a178d5f2ec12025-08-20T04:00:55ZengMDPI AGRemote Sensing2072-42922025-08-011715271310.3390/rs17152713Phenology-Aware Machine Learning Framework for Chlorophyll Estimation in Cotton Using Hyperspectral ReflectanceChunbo Jiang0Yi Cheng1Yongfu Li2Lei Peng3Gangshang Dong4Ning Lai5Qinglong Geng6Agricultural Engineering and Information Technology, College of Resources and Environment, Xinjiang Agricultural University, Urumqi 830052, ChinaAgricultural Engineering and Information Technology, College of Resources and Environment, Xinjiang Agricultural University, Urumqi 830052, ChinaXinjiang Academy of Agricultural Sciences, Resource and Environmental Information Technology Innovation Team, Urumqi 830091, ChinaXinjiang Academy of Agricultural Sciences, Resource and Environmental Information Technology Innovation Team, Urumqi 830091, ChinaXinjiang Academy of Agricultural Sciences, Resource and Environmental Information Technology Innovation Team, Urumqi 830091, ChinaXinjiang Academy of Agricultural Sciences, Resource and Environmental Information Technology Innovation Team, Urumqi 830091, ChinaXinjiang Academy of Agricultural Sciences, Resource and Environmental Information Technology Innovation Team, Urumqi 830091, ChinaAccurate and non-destructive monitoring of leaf chlorophyll content (LCC) is essential for assessing crop photosynthetic activity and nitrogen status in precision agriculture. This study introduces a phenology-aware machine learning framework that combines hyperspectral reflectance data with various regression models to estimate leaf chlorophyll content (LCC) in cotton at six key reproductive stages. Field experiments utilized synchronized spectral and SPAD measurements, incorporating spectral transformations—such as vegetation indices (VIs), first-order derivatives, and trilateration edge parameters (TEPs, a new set of geometric metrics for red-edge characterization)—for evaluation. Five regression approaches were evaluated, including univariate and multivariate linear models, along with three machine learning algorithms: Random Forest, K-Nearest Neighbor, and Support Vector Regression. Random Forest consistently outperformed the other models, achieving the highest R<sup>2</sup> (0.85) and the lowest RMSE (4.1) during the bud stage. Notably, the optimal prediction accuracy was achieved with fewer than five spectral features. The proposed framework demonstrates the potential for scalable, stage-specific monitoring of chlorophyll dynamics and offers valuable insights for large-scale crop management applications.https://www.mdpi.com/2072-4292/17/15/2713chlorophyll estimationhyperspectral reflectancerandom forest regressionphenological stagesvegetation indicescotton |
| spellingShingle | Chunbo Jiang Yi Cheng Yongfu Li Lei Peng Gangshang Dong Ning Lai Qinglong Geng Phenology-Aware Machine Learning Framework for Chlorophyll Estimation in Cotton Using Hyperspectral Reflectance Remote Sensing chlorophyll estimation hyperspectral reflectance random forest regression phenological stages vegetation indices cotton |
| title | Phenology-Aware Machine Learning Framework for Chlorophyll Estimation in Cotton Using Hyperspectral Reflectance |
| title_full | Phenology-Aware Machine Learning Framework for Chlorophyll Estimation in Cotton Using Hyperspectral Reflectance |
| title_fullStr | Phenology-Aware Machine Learning Framework for Chlorophyll Estimation in Cotton Using Hyperspectral Reflectance |
| title_full_unstemmed | Phenology-Aware Machine Learning Framework for Chlorophyll Estimation in Cotton Using Hyperspectral Reflectance |
| title_short | Phenology-Aware Machine Learning Framework for Chlorophyll Estimation in Cotton Using Hyperspectral Reflectance |
| title_sort | phenology aware machine learning framework for chlorophyll estimation in cotton using hyperspectral reflectance |
| topic | chlorophyll estimation hyperspectral reflectance random forest regression phenological stages vegetation indices cotton |
| url | https://www.mdpi.com/2072-4292/17/15/2713 |
| work_keys_str_mv | AT chunbojiang phenologyawaremachinelearningframeworkforchlorophyllestimationincottonusinghyperspectralreflectance AT yicheng phenologyawaremachinelearningframeworkforchlorophyllestimationincottonusinghyperspectralreflectance AT yongfuli phenologyawaremachinelearningframeworkforchlorophyllestimationincottonusinghyperspectralreflectance AT leipeng phenologyawaremachinelearningframeworkforchlorophyllestimationincottonusinghyperspectralreflectance AT gangshangdong phenologyawaremachinelearningframeworkforchlorophyllestimationincottonusinghyperspectralreflectance AT ninglai phenologyawaremachinelearningframeworkforchlorophyllestimationincottonusinghyperspectralreflectance AT qinglonggeng phenologyawaremachinelearningframeworkforchlorophyllestimationincottonusinghyperspectralreflectance |